CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding

Abstract:Accurate detection and localization of traumatic injuries in abdominal CT remain challenging because voxel-level annotations are limited and expensive to obtain. We present a label-efficient framework for 3D abdominal trauma detection that combines self-supervised pretraining with semi-supervised transformer-based detection. First, we use Masked Image Modeling (MIM) on 1098 CT volumes to pretrain a 3D U-Net encoder for anatomical representation learning. Next, we adapt V-DETR to dense volumetric CT through a feature adapter that converts the encoder feature grid into a compact token sequence for transformer decoding. The pretrained encoder is then integrated with V-DETR and 3D Vertex Relative Position Encoding (3D V-RPE) to improve the localization of irregularly shaped injuries. Finally, semi-supervised teacher-student consistency regularization leverages 2,000 additional unlabeled volumes during detector training. To the best of our knowledge, this is the first application of a 3D DETR-style detector to the RSNA abdominal trauma detection task. On this benchmark, the proposed method achieves 31.33% test mAP@0.50 using only 78 labeled training volumes, corresponding to a 1.53x improvement over supervised-only training. These results show that combining medical-domain pretraining with semi-supervised learning is an effective strategy for label-scarce 3D medical detection.

v2: Updated results with corrected dataset split. Revised Table 1 (mAP@0.50: 31.33% SSL vs 20.45% baseline, 1.53x improvement; mAP@0.75: 30.95% vs 10.45%, 2.96x improvement). Updated validation curves showing stable convergence. No methodology changes. 7 pages, 4 figures, 2 tables. Code: this https URL

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

arXiv:2603.12514 [cs.CV]

(or arXiv:2603.12514v2 [cs.CV] for this version)